language:
- en
license: mit
library_name: transformers
tags:
- LCARS
- Star-Trek
- 128k-Context
- mistral
- chemistry
- biology
- finance
- legal
- art
- code
- medical
- text-generation-inference
pipeline_tag: text2text-generation
model-index:
- name: LCARS_AI_StarTrek_Computer
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 35.83
name: strict accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/LCARS_AI_StarTrek_Computer
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 21.78
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/LCARS_AI_StarTrek_Computer
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 4.08
name: exact match
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/LCARS_AI_StarTrek_Computer
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 2.35
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/LCARS_AI_StarTrek_Computer
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 7.44
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/LCARS_AI_StarTrek_Computer
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 16.2
name: accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=LeroyDyer/LCARS_AI_StarTrek_Computer
name: Open LLM Leaderboard
If anybody has star trek data please send as this starship computer database archive needs it!
then i can correctly theme this model to be inside its role as a starship computer : so as well as any space dara ffrom nasa ; i have collected some mufon files which i am still framing the correct prompts for ; for recall as well as interogation : I shall also be adding a lot of biblical data and historical data ; from sacred texts; so any generated discussions as phylosophers discussing ancient history and how to solve the problems of the past which they encountered ; in thier lifes: using historical and factual data; as well as playig thier roles after generating a biography and character role to the models to play: they should also be amazed by each others acheivements depending on thier periods: we need multiple role and characters for these discussions: as well as as much historical facts and historys as possible to enhance this models abitlity to dicern ancient aliens truth or false : (so we need astrological, astronomical, as well as sizmological and ecological data for the periods of histroy we know : as well as the unfounded suupositions from youtube subtitles !) another useful source of themed data!
This model is a Collection of merged models via various merge methods : Reclaiming Previous models which will be orphened by thier parent models : THis model is the model of models so it may not Remember some task or Infact remember them all as well as highly perform ! There were some very bad NSFW Merges from role play to erotica as well as various characters and roles downloaded into the model: So those models were merged into other models which had been specifically trained for maths or medical data and the coding operations or even translation:
the models were heavliy dpo trained ; and various newer methodologies installed : the deep mind series is a special series which contains self correction recal, visio spacial ... step by step thinking:
SO the multi merge often fizes these errors between models as well as training gaps :Hopefully they all took and merged well ! Performing even unknown and unprogrammed tasks:
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 14.61 |
| IFEval (0-Shot) | 35.83 |
| BBH (3-Shot) | 21.78 |
| MATH Lvl 5 (4-Shot) | 4.08 |
| GPQA (0-shot) | 2.35 |
| MuSR (0-shot) | 7.44 |
| MMLU-PRO (5-shot) | 16.20 |